1
|
Effects of the nerve growth factor and its carrier protein on the inflammatory response from human monocytes. Fundam Clin Pharmacol 2024. [PMID: 38693600 DOI: 10.1111/fcp.13006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Revised: 03/18/2024] [Accepted: 04/12/2024] [Indexed: 05/03/2024]
Abstract
BACKGROUND The nerve growth factor (NGF) has been previously shown to be involved in cellular proliferation, differentiation, survival, or wound healing. This factor displays a variety of biological effects that yet remain to be explored. Previous data on cell lines show a pro-inflammatory role of NGF on monocytes. OBJECTIVES The objective of the study was to investigate the pro-inflammatory effect of NGF, using a model of fresh human monocytes. METHODS Monocytes obtained from PBMC were exposed to NGF at various concentrations. Alternatively, monocytes were exposed to BSA, the NGF carrier protein without the NGF. Gene expression and cytokine release in the supernatant were monitored. RESULTS We found that NGF increased the expression of pro-inflammatory, chemotactic, and remodeling genes such as interleukin (IL)-1β, IL-6, tumor necrosis factor (TNF)-α, and C-X-C motif ligand (CXCL)8. The protein levels of CXCL8 and matrix metalloproteinase (MMP)-9 were also increased in the cell supernatants following NGF exposure. BSA alone was found to drive part of this response, bringing nuance to the inflammatory potential of the NGF. CONCLUSION These data suggest that NGF is able to enhance monocyte inflammatory responses once cells are stimulated with another signal but is possibly not able to directly activate it. This could have implications for example in patients with bacterial infections, where NGF could worsen the local inflammation by over-activating immune cells.
Collapse
|
2
|
A Deep Reinforcement Learning Strategy for Surrounding Vehicles-Based Lane-Keeping Control. SENSORS (BASEL, SWITZERLAND) 2023; 23:9843. [PMID: 38139694 PMCID: PMC10748354 DOI: 10.3390/s23249843] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/10/2023] [Revised: 12/04/2023] [Accepted: 12/13/2023] [Indexed: 12/24/2023]
Abstract
As autonomous vehicles (AVs) are advancing to higher levels of autonomy and performance, the associated technologies are becoming increasingly diverse. Lane-keeping systems (LKS), corresponding to a key functionality of AVs, considerably enhance driver convenience. With drivers increasingly relying on autonomous driving technologies, the importance of safety features, such as fail-safe mechanisms in the event of sensor failures, has gained prominence. Therefore, this paper proposes a reinforcement learning (RL) control method for lane-keeping, which uses surrounding object information derived through LiDAR sensors instead of camera sensors for LKS. This approach uses surrounding vehicle and object information as observations for the RL framework to maintain the vehicle's current lane. The learning environment is established by integrating simulation tools, such as IPG CarMaker, which incorporates vehicle dynamics, and MATLAB Simulink for data analysis and RL model creation. To further validate the applicability of the LiDAR sensor data in real-world settings, Gaussian noise is introduced in the virtual simulation environment to mimic sensor noise in actual operational conditions.
Collapse
|
3
|
Path Planning and Motion Control of Indoor Mobile Robot under Exploration-Based SLAM (e-SLAM). SENSORS (BASEL, SWITZERLAND) 2023; 23:3606. [PMID: 37050664 PMCID: PMC10099333 DOI: 10.3390/s23073606] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/19/2023] [Revised: 03/27/2023] [Accepted: 03/28/2023] [Indexed: 06/19/2023]
Abstract
Indoor mobile robot (IMR) motion control for e-SLAM techniques with limited sensors, i.e., only LiDAR, is proposed in this research. The path was initially generated from simple floor plans constructed by the IMR exploration. The path planning starts from the vertices which can be traveled through, proceeds to the velocity planning on both cornering and linear motion, and reaches the interpolated discrete points joining the vertices. The IMR recognizes its location and environment gradually from the LiDAR data. The study imposes the upper rings of the LiDAR image to perform localization while the lower rings are for obstacle detection. The IMR must travel through a series of featured vertices and perform the path planning further generating an integrated LiDAR image. A considerable challenge is that the LiDAR data are the only source to be compared with the path planned according to the floor map. Certain changes still need to be adapted into, for example, the distance precision with relevance to the floor map and the IMR deviation in order to avoid obstacles on the path. The LiDAR setting and IMR speed regulation account for a critical issue. The study contributed to integrating a step-by-step procedure of implementing path planning and motion control using solely the LiDAR data along with the integration of various pieces of software. The control strategy is thus improved while experimenting with various proportional control gains for position, orientation, and velocity of the LiDAR in the IMR.
Collapse
|
4
|
Real-Time Sonar Fusion for Layered Navigation Controller. SENSORS 2022; 22:s22093109. [PMID: 35590798 PMCID: PMC9102793 DOI: 10.3390/s22093109] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Revised: 04/06/2022] [Accepted: 04/15/2022] [Indexed: 12/10/2022]
Abstract
Navigation in varied and dynamic indoor environments remains a complex task for autonomous mobile platforms. Especially when conditions worsen, typical sensor modalities may fail to operate optimally and subsequently provide inapt input for safe navigation control. In this study, we present an approach for the navigation of a dynamic indoor environment with a mobile platform with a single or several sonar sensors using a layered control system. These sensors can operate in conditions such as rain, fog, dust, or dirt. The different control layers, such as collision avoidance and corridor following behavior, are activated based on acoustic flow queues in the fusion of the sonar images. The novelty of this work is allowing these sensors to be freely positioned on the mobile platform and providing the framework for designing the optimal navigational outcome based on a zoning system around the mobile platform. Presented in this paper is the acoustic flow model used, as well as the design of the layered controller. Next to validation in simulation, an implementation is presented and validated in a real office environment using a real mobile platform with one, two, or three sonar sensors in real time with 2D navigation. Multiple sensor layouts were validated in both the simulation and real experiments to demonstrate that the modular approach for the controller and sensor fusion works optimally. The results of this work show stable and safe navigation of indoor environments with dynamic objects.
Collapse
|
5
|
Overcoming Challenges of Applying Reinforcement Learning for Intelligent Vehicle Control. SENSORS 2021; 21:s21237829. [PMID: 34883832 PMCID: PMC8659501 DOI: 10.3390/s21237829] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/01/2021] [Revised: 11/18/2021] [Accepted: 11/20/2021] [Indexed: 12/04/2022]
Abstract
Reinforcement learning (RL) is a booming area in artificial intelligence. The applications of RL are endless nowadays, ranging from fields such as medicine or finance to manufacturing or the gaming industry. Although multiple works argue that RL can be key to a great part of intelligent vehicle control related problems, there are many practical problems that need to be addressed, such as safety related problems that can result from non-optimal training in RL. For instance, for an RL agent to be effective it should first cover all the situations during training that it may face later. This is often difficult when applied to the real-world. In this work we investigate the impact of RL applied to the context of intelligent vehicle control. We analyse the implications of RL in path planning tasks and we discuss two possible approaches to overcome the gap between the theorical developments of RL and its practical applications. Specifically, firstly this paper discusses the role of Curriculum Learning (CL) to structure the learning process of intelligent vehicle control in a gradual way. The results show how CL can play an important role in training agents in such context. Secondly, we discuss a method of transferring RL policies from simulation to reality in order to make the agent experience situations in simulation, so it knows how to react to them in reality. For that, we use Arduino Yún controlled robots as our platforms. The results enhance the effectiveness of the presented approach and show how RL policies can be transferred from simulation to reality even when the platforms are resource limited.
Collapse
|
6
|
Abstract
This paper describes a series of studies resulting from the finding that when free floating in weightless conditions with eyes closed, all sense of one's spatial orientation with respect to the aircraft can be lost. But, a touch of the hand to the enclosure restores the sense of spatial anchoring within the environment. This observation led to the exploration of how light touch of the hand can stabilize postural control on Earth even in individuals lacking vestibular function, and can override the effect of otherwise destabilizing tonic vibration reflexes in leg muscles. Such haptic stabilization appears to represent a long loop cortical reflex with contact cues at the hand phase leading EMG activity in leg muscles, which change the center of pressure at the feet to counteract body sway. Experiments on dynamic control of balance in a device programmed to exhibit inverted pendulum behavior about different axes and planes of rotation revealed that the direction of gravity not the direction of balance influences the perceived upright. Active control does not improve the accuracy of indicating the upright vs. passive exposure. In the absence of position dependent gravity shear forces on the otolith organs and body surface, drifting and loss of control soon result and subjects are unaware of their ongoing spatial position. There is a failure of dynamic path integration of the semicircular canal signals, such as occurs in weightless conditions.
Collapse
|
7
|
Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages. SENSORS 2021; 21:s21062032. [PMID: 33805601 PMCID: PMC8001915 DOI: 10.3390/s21062032] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/19/2021] [Revised: 03/11/2021] [Accepted: 03/11/2021] [Indexed: 11/20/2022]
Abstract
The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement learning based approach to autonomous vehicle longitudinal control, where the rule-based safety cages provide enhanced safety for the vehicle as well as weak supervision to the reinforcement learning agent. By guiding the agent to meaningful states and actions, this weak supervision improves the convergence during training and enhances the safety of the final trained policy. This rule-based supervisory controller has the further advantage of being fully interpretable, thereby enabling traditional validation and verification approaches to ensure the safety of the vehicle. We compare models with and without safety cages, as well as models with optimal and constrained model parameters, and show that the weak supervision consistently improves the safety of exploration, speed of convergence, and model performance. Additionally, we show that when the model parameters are constrained or sub-optimal, the safety cages can enable a model to learn a safe driving policy even when the model could not be trained to drive through reinforcement learning alone.
Collapse
|
8
|
On-the-road driving performance of patients with central disorders of hypersomnolence. TRAFFIC INJURY PREVENTION 2021; 22:120-126. [PMID: 33543997 DOI: 10.1080/15389588.2020.1862804] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/13/2020] [Revised: 11/03/2020] [Accepted: 12/07/2020] [Indexed: 06/12/2023]
Abstract
INTRODUCTION Excessive Daytime Sleepiness is a core symptom of narcolepsy and idiopathic hypersomnia, which impairs driving performance. Adequate treatment improves daytime alertness, but it is unclear whether driving performance completely normalizes. This study compares driving performance of patients with narcolepsy and idiopathic hypersomnia receiving treatment to that of healthy controls. METHODS Patients diagnosed with narcolepsy type 1 (NT1, n = 33), narcolepsy type 2 (NT2, n = 7), or idiopathic hypersomnia (IH, n = 6) performed a standardized one-hour on-the-road driving test, measuring standard deviation of lateral position (SDLP). RESULTS Results showed that mean SDLP in patients did not differ significantly from controls, but the 95%CI of the mean difference (+1.02 cm) was wide (-0.72 to +2.76 cm). Analysis of subgroups, however, showed that mean SDLP in NT1 patients was significantly increased by 1.90 cm as compared to controls, indicating impairment. Moreover, four NT1 patients requested to stop the test prematurely due to self-reported somnolence, and two NT1 patients were stopped by the driving instructor for similar complaints. CONCLUSION Driving performance of NT1 patients may still be impaired, despite receiving treatment. No conclusions can be drawn for NT2 and IH patients due to the low sample sizes of these subgroups. In clinical practice, determination of fitness to drive for these patients should be based on an individual assessment in which also coping strategies are taken into account.
Collapse
|
9
|
Simulation of Pulse-Echo Radar for Vehicle Control and SLAM. SENSORS 2021; 21:s21020523. [PMID: 33450957 PMCID: PMC7828404 DOI: 10.3390/s21020523] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Revised: 01/04/2021] [Accepted: 01/05/2021] [Indexed: 11/30/2022]
Abstract
Pulse-echo sensing is the driving principle behind biological echolocation as well as biologically-inspired sonar and radar sensors. In biological echolocation, a single emitter sends a self-generated pulse into the environment which reflects off objects. A fraction of these reflections are captured by two receivers as echoes, from which information about the objects, such as their position in 3D space, can be deduced by means of timing, intensity and spectral analysis. This is opposed to frequency-modulated continuous-wave radar, which analyses the shift in frequency of the returning signal to determine distance, and requires an array of antenna to obtain directional information. In this work, we present a novel simulator which can generate synthetic pulse-echo measurements for a simulated sensor in a virtual environment. The simulation is implemented by replicating the relevant physical processes underlying the pulse-echo sensing modality, while achieving high performance at update rates above 50 Hz. The system is built to perform design space exploration of sensor hardware and software, with the goals of rapid prototyping and preliminary safety testing in mind. We demonstrate the validity of the simulator by replicating real-world experiments from previous work. In the first case, a subsumption architecture vehicle controller is set to navigate an unknown environment using the virtual sensor. We see the same trajectory pattern emerge in the simulated environment rebuilt from the real experiment, as well as similar activation times for the high-priority behaviors (±1.9%), and low-priority behaviors (±0.2%). In a second experiment, the simulated signals are used as input to a biologically-inspired direct simultaneous mapping and localization (SLAM) algorithm. Using only path integration, 83% of the positional errors are larger than 10 m, while for the SLAM algorithm 95% of the errors are smaller than 3.2m. Additionally, we perform design space exploration using the simulator. By creating a synthetic radiation pattern with increased spatiospectral variance, we are able to reduce the average localization error of the system by 11%. From these results, we conclude that the simulation is sufficiently accurate to be of use in developing vehicle controllers and SLAM algorithms for pulse-echo radar sensors.
Collapse
|
10
|
Alcohol use patterns and their association with sober driver vehicle control in high fidelity driving simulation. TRAFFIC INJURY PREVENTION 2020; 21:S150-S154. [PMID: 33179979 DOI: 10.1080/15389588.2020.1829909] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
OBJECTIVE To examine the relationship between patterns of alcohol use, as determined by the Alcohol Use Disorders Identification Test, and vehicle control measures in high fidelity driving simulation among adult sober drivers. METHODS Baseline data (BAC = 0.00%; N = 108) from a larger study aimed at using high-fidelity driving simulation (National Advanced Driving Simulator) to evaluate the feasibility of vehicle-based sensors to identify alcohol impairment were analyzed. Driving simulation scenarios included driving on urban, interstate, and rural roadways. The independent variable was the pattern of alcohol use measured with the Alcohol Use Disorder Identification Test (AUDIT). Dependent variables included one lateral vehicle control measure (i.e., standard deviation of lane position (SDLP)) and one longitudinal vehicle control measure (i.e., average speed relative to the speed limit) in high fidelity driving simulation. Multivariable linear regression was used to examine the associations between patterns of alcohol use and vehicle control measures. RESULTS Total AUDIT scores ≥8 was positively associated with SDLP. Increased frequency of drinking was associated with decreased SDLP and increased average speed relative to the speed limit. Increased reports of blackouts and alcohol-related injury were associated with increased average speed relative to the speed limit. Driver performance (SDLP, average speed relative to the speed limit) was related to additional factors such as driver experience, age, marital status, and driving context. CONCLUSIONS The findings support our hypothesis that the AUDIT score and responses to individual AUDIT questions, among sober drivers, relates to vehicle control measures. Overall, our data highlight two important themes: 1) a need to further integrate alcohol use metrics with high-fidelity driving simulation studies to understand how drinking experience can relate to driver behavior and vehicle control and 2) the opportunity to integrate clinical perspectives with driving simulation research to strengthen clinically oriented alcohol-misuse prevention efforts.
Collapse
|
11
|
Quantifying vehicle control from physiology in type 1 diabetes. TRAFFIC INJURY PREVENTION 2019; 20:S26-S31. [PMID: 31617757 DOI: 10.1080/15389588.2019.1665176] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/05/2019] [Revised: 08/28/2019] [Accepted: 09/03/2019] [Indexed: 06/10/2023]
Abstract
Objective: Our goal is to measure real-world effects of at-risk driver physiology on safety-critical tasks like driving by monitoring driver behavior and physiology in real-time. Drivers with type 1 diabetes (T1D) have an elevated crash risk that is linked to abnormal blood glucose, particularly hypoglycemia. We tested the hypotheses that (1) T1D drivers would have overall impaired vehicle control behavior relative to control drivers without diabetes, (2) At-risk patterns of vehicle control in T1D drivers would be linked to at-risk, in-vehicle physiology, and (3) T1D drivers would show impaired vehicle control with more recent hypoglycemia prior to driving.Methods: Drivers (18 T1D, 14 control) were monitored continuously (4 weeks) using in-vehicle sensors (e.g., video, accelerometer, speed) and wearable continuous glucose monitors (CGMs) that measured each T1D driver's real-time blood glucose. Driver vehicle control was measured by vehicle acceleration variability (AV) across lateral (AVY, steering) and longitudinal (AVX, braking/accelerating) axes in 45-second segments (N = 61,635). Average vehicle speed for each segment was modeled as a covariate of AV and mixed-effects linear regression models were used.Results: We analyzed 3,687 drives (21,231 miles). T1D drivers had significantly higher overall AVX, Y compared to control drivers (BX = 2.5 × 10-2BY = 1.6 × 10-2, p < 0.01)-which is linked to erratic steering or swerving and harsh braking/accelerating. At-risk vehicle control patterns were particularly associated with at-risk physiology, namely hypo- and hyperglycemia (higher overall AVX,Y). Impairments from hypoglycemia persisted for hours after hypoglycemia resolved, with drivers who had hypoglycemia within 2-3 h of driving showing higher AVX and AVY. State Department of Motor Vehicle records for the 3 years preceding the study showed that at-risk T1D drivers accounted for all crashes (N = 3) and 85% of citations (N = 13) observed.Conclusions: Our results show that T1D driver risk can be linked to real-time patterns of at-risk driver physiology, particularly hypoglycemia, and driver risk can be detected during and prior to driving. Such naturalistic studies monitoring driver vehicle controls can inform methods for early detection of hypoglycemia-related driving risks, fitness to drive assessments, thereby helping to preserve safety in at-risk drivers with diabetes.
Collapse
|
12
|
Low-Cost FPGA-Based Electronic Control Unit for Vehicle Control Systems. SENSORS 2019; 19:s19081834. [PMID: 30999643 PMCID: PMC6515210 DOI: 10.3390/s19081834] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/19/2019] [Revised: 03/29/2019] [Accepted: 04/13/2019] [Indexed: 11/17/2022]
Abstract
The development of new control algorithms in vehicles requires high economic resources, mainly due to the use of generic real-time instrumentation and control systems. In this work, we proposed a low-cost electronic control unit (ECU) that could be used for both development and implementation. The proposed electronic system used a hybrid system on chip (SoC) between a field-programmable gate array (FPGA) and an Advanced RISC (reduced instruction set computer) Machine (ARM) processor that allowed the execution of parallel tasks, fulfilling the real-time requirements that vehicle controls demand. Another feature of the proposed electronic system was the recording of measured data, allowing the performance of the implemented algorithm to be evaluated. All this was achieved by using modular programming that, without the need for a real-time operating system, executed the different tasks to be performed, exploiting the parallelism offered by the FPGA as well as the dual core of the ARM processor. This methodology facilitates the transition between the designing, testing, and implementation stages in the vehicle. In addition, our system is programmed with a single binary file that integrates the code of all processors as well as the hardware description of the FPGA, which speeds up the updating process. In order to validate and demonstrate the performance of the proposed electronic system as a tool for the development and implementation of control algorithms in vehicles, a series of tests was carried out on a test bench. Different traction control system (TCS) algorithms were implemented and the results were compared.
Collapse
|
13
|
Abstract
Many traffic accidents take place throughout the world every day claiming lives as well as commodities and people involved in the accidents have to stay long periods at the hospitals. Traffic accidents are caused by many reasons. One of the reasons is the driver's having a heart attack just before the accident took place. If the heartbeat of the driver can continuously be measured, then most probably one of the reasons of traffic accidents can be eliminated. The designed model aims to measure the driver's heartbeat using infrared imaging. Some car models already have a driver heartbeat monitoring system and it measures the heartbeats by using the back seat electrodes. But these systems are expensive and unique to their models and what is more; its adaptation to other car models can pose a difficulty. Implementing on the car's rear-view mirror this new design monitoring system is very cheap and also it can be mounted to all motor vehicles easily.
Collapse
|
14
|
Direction of balance and perception of the upright are perceptually dissociable. J Neurophysiol 2015; 113:3600-9. [PMID: 25761954 DOI: 10.1152/jn.00737.2014] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2014] [Accepted: 03/10/2015] [Indexed: 11/22/2022] Open
Abstract
We examined whether the direction of balance rather than an otolith reference determines the perceived upright. Participants seated in a device that rotated around the roll axis used a joystick to control its motion. The direction of balance of the device, the location where it would not be accelerated to either side, could be offset from the gravitational vertical, a technique introduced by Riccio, Martin, and Stoffregen (J Exp Psychol Hum Percept Perform 18: 624-644, 1992). Participants used the joystick to align themselves in different trials with the gravitational vertical, the direction of balance, the upright, or the direction that minimized oscillations. They pressed the joystick trigger whenever they thought they were at the instructed orientation. Achieved angles for the "align with gravity" and "align with the upright" conditions were not different from each other and were significantly displaced past the gravitational vertical opposite from the direction of balance. Mean indicated angles for align with gravity and align with the upright coincided with the gravitational vertical. Both mean achieved and indicated angles for the "minimize oscillations" and "align with the direction of balance" conditions were significantly deviated toward the gravitational vertical. Three control experiments requiring self-settings to instructed orientations only, perceptual judgments only, and perceptual judgments during passive exposure to dynamic roll profiles confirmed that perception of the upright is determined by gravity, not by the direction of balance.
Collapse
|